smolvla_insert_candle

Fine-tuned SmolVLA for bimanual SO101 (12-dim action/state).

Base model	lerobot/smolvla_base
Dataset	villekuosmanen/armnetbench_insert_candle
Checkpoints	5,000 and 10,000 steps
Training	Vast.ai 4xH100, batch 128, ~8.5h total
Action dim	12 (bimanual SO101, 6 per arm)
Cameras	top, left_wrist, right_wrist
W&B	smolvla_insert_candle

Checkpoints

• checkpoints/005000/pretrained_model/
• checkpoints/010000/pretrained_model/

Usage

from lerobot.policies.smolvla.modeling_smolvla import SmolVLAPolicy

policy = SmolVLAPolicy.from_pretrained("pravsels/smolvla_insert_candle", subfolder="checkpoints/010000/pretrained_model")

Training Logs

Full training curves and metrics: https://wandb.ai/pravsels/smolvla_insert_candle/runs/j8rzs0bb